Optimal Aggregation of Binary Classifiers for Multiclass Cancer Diagnosis Using Gene Expression Profiles

Multiclass classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. There have been many studies of aggregating binary classifiers to construct a multiclass classifier based on one-versus-the-rest (1R), one-versus-one (11), or other coding strategies, as well as some comparison studies between them. However, the studies found that the best coding depends on each situation. Therefore, a new problem, which we call the ldquooptimal coding problem,rdquo has arisen: how can we determine which coding is the optimal one in each situation? To approach this optimal coding problem, we propose a novel framework for constructing a multiclass classifier, in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. Although there is no a priori answer to the optimal coding problem, our weight tuning method can be a consistent answer to the problem. We apply this method to various classification problems including a synthesized data set and some cancer diagnosis data sets from gene expression profiling. The results demonstrate that, in most situations, our method can improve classification accuracy over simple voting heuristics and is better than or comparable to state-of-the-art multiclass predictors.     

Teratogens as Anticancer Drugs

Most anticancer drugs are teratogens, merely because they target vital cellular functions. Conversely, some plants produce agents that intentionally target embryonic signaling pathways, precisely to cause birth defects if pregnant animals eat such plants. Cyclopamine, a teratogen produced by a flowering plant, inhibits the Hh/Gli pathway, causing developmental defects such as cyclopia (one eye in the middle of the face). In theory, selective teratogens may suppress cancer cells that re-activate embryonic pathways, while sparing most normal cells. I discuss the potential (and limits) of teratogens in cancer therapy, linking diverse topics from morning sickness of pregnancy, embryonic pathways and poisonous plants to the mechanism of action of anticancer teratogens and their combinations with less selective cytotoxic agents.     

Conceptualizing multi-ethnic societies

We examine the process of linguistic adaptation among children of immigrants and the extent to which distinct language types exist between foreign monolingualism and a full transition to English. While complete linguistic assimilation remains the normative outcome and is widely perceived as desirable, we examine alternative theories holding that selective rather than full acculturation is a preferable alternative for immigrant children and their families. For this purpose we contrast effects of fluent bilingualism, indicative of selective acculturation, with other types of linguistic adaptation on various measures of family conflict, solidarity and personality. The data come from the Children of Immigrants Longitudinal Study [CILS], which have been used in several previous studies of the second generation. We use this data-set to test new hypotheses on the interactive effects of parental and children's knowledge of English on family relations and personality outcomes and to examine the effects of gender differences throughout the process. We find that a plurality of second generation linguistic adaptation types exists in reality and that, among them, fluent bilingualism is consistently preferable. Theoretical and policy implications of these and other results are discussed.     

肺癌分子靶向药物研究进展

本文就表皮生长因子受体(EGFR)酪氨酸激酶抑制剂、EGFR单克隆抗体、肿瘤血管生成因子(VEGF)受体抑制荆、内皮抑素以及一些多靶点药物等靶向药物在肺癌中的临床研究和应用进行综述。     

Facile Synthesis of New Hybrid 2-Quinlolinone Derivatives Structures as Anticancer Drugs for Breast Cancer Treatment

Russian Journal of Bioorganic Chemistry - A new series of hybrid 2-quinolinone derivatives were synthesized and confirmed using IR, 1H NMR, 13C NMR, and elemental analyses. The cytotoxic activities...     

Nonsteroidal Anti-inflammatory Drugs as Emerging Contaminants

Microbiology - Nonsteroidal anti-inflammatory drugs (NSAIDs) are a group of pharmaceuticals widely used for medical and veterinary purposes. NSAIDs have been found in nanograms and micrograms in...     

Keystone Symposium on Antibodies as Drugs

The symposium on Antibodies as Drugs, organized by Keystone Symposia and chaired by J. Marks, (University of California Los Angeles, USA), E.S. Ward (University of Texas Southwestern Medical Center, USA) and L. Weiner (Georgetown University Medical Center, USA), was held in Whistler, British Columbia. This Canadian Rockies village, which will host the 2010 Olympic Games, served as an enchanting backdrop to the meeting. The >350 speakers and attendees included scientists from major pharmaceutical firms, e.g., Abbott, MedImmune/Astra Zeneca, Bristol-Myers Squibb, Merck & Co, Pfizer, Sanofi-Aventis, Schering, GlaxoSmithKline, Eli Lilly, Hoffmann LaRoche, Novartis, Wyeth, and biotechnology companies, e.g., Ablynx, Medarex, Morphosys, GenMab, Amgen, Genentech, ImmunoGen, Agensys, Domantis, Biogen Idec, Centocor, LFB, Micromet, PDL Biopharma, Borean Pharma, Dyax Corp, Symphogen, Syntonix. Academic research groups at Imperial College London, University of Oxford, ETH Zürich, Scripps, Institute Cochin, Karolinska Institute, Utrecht University, Harvard Medical School, Massachusetts Institute of Technology, Baylor College, Paul Ehrlich Institute, University of California San Francisco, University of California San Diego, University of Nantes, University of Tours, and Ludwig Institute were also represented, as were regulatory authorities, including the US Food and Drug Administration, National Institutes of Health and the Public Health Agency of Canada). The meeting was very interactive, and included thoughtful exchanges during the different sessions and networking events.     

典型内分泌药物用于乳腺癌治疗的研究进展

雌激素与乳腺癌细胞中的雌激素受体(estrogen receptors,ERs)结合后,通过基因组和非基因组信号途径调节细胞的生长和增殖,从而参与乳腺癌的发生和发展。内分泌药物作为一类典型的外源雌激素,它能通过调控不同靶组织中的雌激素水平来抑制细胞的增殖。深入开展内分泌药物研究可为乳腺癌的内分泌治疗提供指导。现综述了典型内分泌药物在乳腺癌治疗中的作用机制,并对ERs及其相关信号通路中用于乳腺癌治疗的可能靶点进行了讨论,以期为潜在的内分泌药物研究提供参考。     

Prediction and Prioritization of Rare Oncogenic Mutations in the Cancer Kinome Using Novel Features and Multiple Classifiers

Cancer is a genetic disease that develops through a series of somatic mutations, a subset of which drive cancer progression. Although cancer genome sequencing studies are beginning to reveal the mutational patterns of genes in various cancers, identifying the small subset of “causative” mutations from the large subset of “non-causative” mutations, which accumulate as a consequence of the disease, is a challenge. In this article, we present an effective machine learning approach for identifying cancer-associated mutations in human protein kinases, a class of signaling proteins known to be frequently mutated in human cancers. We evaluate the performance of 11 well known supervised learners and show that a multiple-classifier approach, which combines the performances of individual learners, significantly improves the classification of known cancer-associated mutations. We introduce several novel features related specifically to structural and functional characteristics of protein kinases and find that the level of conservation of the mutated residue at specific evolutionary depths is an important predictor of oncogenic effect. We consolidate the novel features and the multiple-classifier approach to prioritize and experimentally test a set of rare unconfirmed mutations in the epidermal growth factor receptor tyrosine kinase (EGFR). Our studies identify T725M and L861R as rare cancer-associated mutations inasmuch as these mutations increase EGFR activity in the absence of the activating EGF ligand in cell-based assays.     

Pooled Human Immunoglobulin Preparations as Immunomodulating Drugs

Molecular Biology - It is time to celebrate the 125th anniversary of the first successful attempt to develop and use a specific high-titer antitoxic serum for treating diphtheria, a deadly...     

A Systematic Comparison of Supervised Classifiers

Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM). In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.     

Good Quality Locally Procured Drugs Can Be as Effective as Internationally Quality Assured Drugs in Treating Multi-Drug Resistant Tuberculosis

Background

Owing toGiven the high costs of drugs to treat multi-drug resistant tuberculosis (MDR-TB), the Green Light Committee (GLC) initiative enables TB programs to procure quality-assured drugs at reduced prices. Despite price reductions, internationally quality assured (IQA) drugs can be more expensive than locally procured drugs. There is little evidence to inform decision-makers about whether IQA drugs are more effective than local drugs. This is the first study to compare outcomes between MDR-TB patients treated using IQA, and locally procured drugs in the same hospitals during the same time period.

Methods/Findings

A retrospective cohort study was conducted in three hospitals across Pakistan. Data on baseline characteristics and treatment outcomes during the first six months of treatment were extracted from hospital records of adult culture-positive pulmonary MDR-TB patients starting treatment between January 2011 and June 2012. Two cohorts were defined: patients receiving IQA drugs, and patients receiving locally procured non-IQA drugs. Data were analysed using Kaplan-Meier curves and Cox proportional hazards regression. The primary outcome compared between cohorts was time to culture conversion. Of 231 patients, 90 were in the IQA and 141 in the non-IQA cohorts. Baseline characteristics were similar except for higher frequency of quinolone resistance in the IQA cohort. Overall, 193 patients (84%) culture converted. Culture conversion was not faster in the IQA cohort; the median time was 81 and 68 days in the IQA and non-IQA cohorts, respectively. Unadjusted and adjusted hazard ratios for culture conversion in IQA verses non-IQA cohorts were 0.82 (95%-CI, 0.62-1.10) and 0.95 (95%-CI, 0.66-1.36) respectively.

Conclusions

Use of good quality, locally procured drugs can be effective in treating MDR-TB, may involve lower costs than using IQA drugs and could strengthen developing country drug quality assurance systems. This may be a suitable alternative in lieu of or whilst awaiting arrival of internationally procured medicines.     

Engineering Antibodies as Drugs: Principles and Practice

Over the last forty years, recombinant antibodies have been transformed from an unproven experimental approach to a therapeutic modality with multiple success stories in the treatment of cancer, inflammation, infections and cardiometabolic diseases. Owing to their high affinity and selectivity for the target antigen, their multimodal tunable mode of action, their modular nature and long half-life, antibodies now hold prominent positions in the pipelines of major biopharmaceutical companies. In this brief report, I aim to highlight the themes that have shaped the therapeutic antibody engineering as it exists today and to offer a personal perspective on its future developments. Distinct antibody engineering history, developments and trends in Russian Federation will not be discussed since they are detailed elsewhere in this journal issue.     

Hot Cuisine as a Source of Anti-Inflammatory Drugs

The shift in nutritional sciences from survival and safety to the promotion of well-being has led to systematic investigations on the biological activity of natural products of dietary origin, questioning the assumption that food plants contain little if any secondary metabolites apart those revealed by our senses and responsible for their colour, taste, and flavour. With 25% of the human population consuming chilli pepper every day, capsaicin is the most important pharmacological agent we get from our diet, and the study of its pungency set in motion a multidisciplinary investigation that ultimately led to the discovery of vanilloid receptors (TRPVs), a class of ion channels involved in thermo-, chemo-, and mechanosensation, and whose malfunctioning is implicated in neurogenic inflammation and a host of other pathological conditions. A series of studies centred on the modification of capsaicin will be described, focusing on a) the preparation of a library of unnatural natural capsaicinoids and the identification of leads with the lipophilic C-moiety amenable to structure-activity study, and b) the reversal of the biological activity of capsaicin from a TRPV1 agonist into an antagonist by modification of its vanillyl moiety.     

Analysis of FDA Approved Anticancer Drugs Reveals the Future of Cancer Therapy

This review discusses 26 new anticancer drugs approved by the FDA in the past decade. Based on their targets, these anticancer agents can be divided into three groups. First group contains cancer-selective or semi-selective drugs that are effective in rare kinase-addictive cancers. For other malignancies, semi-selective drugs have to be judiciously combined with non-selective agents. The second group includes analogs of classic cytotoxic agents such as DNA alkylating agents, nucleoside analogs, and anti-microtubule agents. As expected, they have a marginal advantage over the existing cytotoxic drugs, nevertheless are more effective (in common cancers) than semi-selective agents. The third is a diverse group of tissue-selective agents that essentially attack the normal tissues of tumor origin and thus, exploit the tissue-specific similarities between normal and cancer cells. Our analysis predicts that monotherapy with semi-selective agents will be limited to rare cancers. In most cancers however, two anticancer strategies may be most fruitful: (a) combinations of cytotoxic drugs with semi-selective agents aimed at matching targets and (b) tissue-selective therapy aimed at normal and tumor cells of the same tissues.     

Increase in Bacterial Resistance to Antibiotics after Cancer Therapy with Platinum-Based Drugs

The use of platinum-based anticancer drugs is limited by both their side effects and their effect on normal microflora’s metagenome. Drugs that possess mutagenic and genotoxic properties may cause mutations in microbial genomes that contribute to the emergence of resistance to antimicrobial preparations and the development of complications after chemotherapy. The effects of cisplatin and oxaliplatin on microorganisms were studied using bacterial biosensors—E. coli strains MG1655 pKatG-lux, which reacts to the generation of hydrogen peroxide; MG1655 pSoxS-lux, which reacts to the superoxide anion radical; and the MG1655 pColD-lux strain, which detects DNA damage. The biosensor tests demonstrated high levels of genotoxicity for both drugs and some differences in the spectrum of reactive oxygen species generated. Ascorbate reduced genotoxicity of cisplatin by 41%. Nonlethal doses of cisplatin induced a three- to sevenfold increase in the frequency of the mutations that confer the resistance of E. coli to rifampicin and ciprofloxacin. Ascorbate also reduced frequency of the mutations by 65%. Thus, the effect of these drugs was probably associated with the generation of reactive oxygen species and induction of SOS response. The risk of secondary antibiotic-resistant infections may be decreased by applying antioxidants and antimutagens. At the same time, these increases may also decrease the anti-tumoral action of these compounds.